SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.13678 · 2020

Designing Network Design Spaces

arXiv · PDF · Open in the Atlas

Code that ran

48 of 53 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 5 honoured the contract we drafted, 0 violated it and 34 have no contract verdict; 9 failures of our instrument; 5 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2003.13678.json · badge: /api/ran/2003.13678.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Alessiacosmos/Basic-RegNet-pytorch community (classifier label)
classifier basis not recorded on the link
14 ran · 3 no recorded run
PaperCodeReview/RegNet-TF community (classifier label)
classifier basis not recorded on the link
14 ran · 1 no recorded run
ZHANGHeng19931123/MutualGuide community (classifier label)
classifier basis not recorded on the link
14 ran · 0 no recorded run
wilile26811249/RegNet community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
yhhhli/regnet-pytorch community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/model/anynet.py
code served (permissive licence) · get_code("2f49808e608b8c96")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned KerasTensor. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
import numpy as np

# Create a small input tensor (batch=2, height=4, width=4, channels=3)
input_tensor = tf.keras.Input(shape=(4, 4, 3))

# Create a dummy args parameter (the function uses it but doesn't reference attributes)
args = None

# Define features, strides, and name
features = 16
strides = 1
name = "block"

# Construct the ARGS dictionary
ARGS = {
    "args": args,
    "x": input_tensor,
    "features": features,
    "strides": strides,
    "name": name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type KerasTensor — a KerasTensor output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ResBlock Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/model/anynet.py
code served (permissive licence) · get_code("2fc21a3ff370f732")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 4, dtype family float, shape (2, 4, 4, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
import numpy as np

# Set seed for reproducibility
np.random.seed(0)
tf.random.set_seed(0)

# Create a small input tensor: batch_size=2, height=4, width=4, channels=3
x = tf.random.normal((2, 4, 4, 3))

# Define args dict with all parameters
ARGS = {
    'args': None,  # The function accepts 'args' but doesn't use it
    'x': x,
    'features': 8,  # Number of output filters
    'strides': 1,  # Stride for convolution
    'name': 'resblock',  # Name prefix for layers
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (2, 4, 4, 8) — shape (2, 4, 4, 8) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ResBottleneckBlock Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/model/anynet.py
code served (permissive licence) · get_code("e4fa2e354a4ccd53")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 4, dtype family float, shape (2, 8, 8, 64) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
from tensorflow.keras.layers import Input
from tensorflow.keras.models import Model

class Args:
    def __init__(self):
        self.bottleneck_ratio = 4
        self.group_width = 1

# Create a minimal args object
args = Args()

# Create input tensor (batch=2, height=8, width=8, channels=16)
input_tensor = tf.random.normal((2, 8, 8, 16))

# Parameters for the function
features = 64
strides = 1
name = 'resblock'

ARGS = {
    'args': args,
    'x': input_tensor,
    'features': features,
    'strides': strides,
    'name': name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (2, 8, 8, 64) — shape (2, 8, 8, 64) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
accuracy Ran
ran on a synthesized input
wilile26811249/RegNet/utils.py
code served (permissive licence) · get_code("f04c9abd65570251")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors for the accuracy function
batch_size = 2
num_classes = 4

# output: logits tensor of shape (batch_size, num_classes)
output = torch.randn(batch_size, num_classes)

# target: ground truth class indices of shape (batch_size,)
target = torch.tensor([0, 2])

# topk: tuple of k values to compute accuracy for
topk = (1, 2)

ARGS = {
    "output": output,
    "target": target,
    "topk": topk,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
adjust_ws_gs_comp Ran
ran on a synthesized input
yhhhli/regnet-pytorch/CIFAR10/models/regnet.py
code served (permissive licence) · get_code("776c7e0f77f8b8e1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function adjust_ws_gs_comp takes three parameters:
# - ws: list of widths (integers)
# - bms: list of bottleneck multipliers (floats between 0 and 1)
# - gs: list of group sizes (integers)

# Looking at the function body:
# - ws is zipped with bms to compute ws_bot
# - gs is zipped with ws_bot to compute min values
# - ws_bot is zipped with g to quantize
# - ws_bot is zipped with bms to compute final ws
# All operations are list comprehensions that iterate, so these should be lists

# Create small distinct-sized lists for testing
ws = [64, 128, 256]  # widths
bms = [0.25, 0.5, 0.75]  # bottleneck multipliers (floats)
gs = [4, 8, 16]  # group sizes

ARGS = {
    "ws": ws,
    "bms": bms,
    "gs": gs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
build_training_folder Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/log_output.py
code served (permissive licence) · get_code("c804dfc430391ebb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
from datetime import datetime

# The function uses:
# - basic_dir: a string path to a directory
# We need to provide a temporary directory that exists

temp_base_dir = tempfile.mkdtemp()

ARGS = {
    "basic_dir": temp_base_dir,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
callback_checkpoint Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/callback.py
code served (permissive licence) · get_code("f3b3cc6d74abcfcb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ModelCheckpoint. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os

ARGS = {
    "filepath": os.path.join(tempfile.gettempdir(), "model_checkpoint.h5"),
    "monitor": "val_loss",
    "verbose": 1,
    "mode": "min",
    "save_best_only": True,
    "save_weights_only": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ModelCheckpoint — a ModelCheckpoint output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ModelCheckpoint output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
callback_epochlogger Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/callback.py
code served (permissive licence) · get_code("300864db1e3cdd90")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned CSVLogger. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os

# Create a temporary directory and file for the CSV logger
temp_dir = tempfile.mkdtemp()
temp_filename = os.path.join(temp_dir, "training_log.csv")

ARGS = {
    "filename": temp_filename,
    "separator": ",",
    "append": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CSVLogger — a CSVLogger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CSVLogger output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
channel_shuffle Ran
ran; our contract draft was wrong, not the code
ZHANGHeng19931123/MutualGuide/models/backbone/shufflenet_backbone.py
pointer only (licence: MIT); the stored copy get_code serves, from ddghost/new_darts, is pointer only (licence: NONE) · get_code("b9da06d4f527dd6c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ddghost/new_darts, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

check_arguments Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/common.py
code served (permissive licence) · get_code("129adedbc3f353c4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Namespace. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from argparse import Namespace

# Create a simple namespace object with the required attributes
args = Namespace(
    src_path='/tmp/src',
    data_path='/tmp/data',
    result_path='/tmp/result'
)

ARGS = {'args': args}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
check_overlap Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/search_space.py
code served (permissive licence) · get_code("733d2079c07e80b7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile

# Create a temporary directory with some files
temp_dir = tempfile.mkdtemp()
with open(os.path.join(temp_dir, "file1.txt"), "w") as f:
    f.write("test")
with open(os.path.join(temp_dir, "file2.txt"), "w") as f:
    f.write("test")

# Create sample configurations
whole_cfg = {
    "model_a": {"lr": 0.001, "batch_size": 32},
    "model_b": {"lr": 0.01, "batch_size": 64},
    "model_c": {"lr": 0.0001, "batch_size": 16}
}

new_cfg = {"lr": 0.005, "batch_size": 48}

ARGS = {
    "path": temp_dir,
    "whole_cfg": whole_cfg,
    "new_cfg": new_cfg
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
color_norm Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/transform.py
code served (permissive licence) · get_code("4f00c5e336d1fab1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (3, 4, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create a small image tensor with shape [C, H, W]
# C=3 (channels), H=4, W=5 for distinctness
img = torch.randn(3, 4, 5, dtype=torch.float32)

# Create mean and std tensors matching the number of channels
mean = torch.tensor([0.5, 0.4, 0.3], dtype=torch.float32)
std = torch.tensor([0.2, 0.25, 0.15], dtype=torch.float32)

ARGS = {
    "img": img,
    "mean": mean,
    "std": std
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (3, 4, 5) — shape (3, 4, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
complexity_batchnorm2d Ran
ran; our contract draft was wrong, not the code
PaperCodeReview/RegNet-TF/model/complexity.py
code served (permissive licence) · get_code("3b4634faa337b07b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function expects:
# - cx: a dictionary with keys 'h', 'w', 'flops', 'params', 'acts'
# - w_in: an integer representing input channel count

cx = {
    'h': 32,
    'w': 32,
    'flops': 1000,
    'params': 500,
    'acts': 2000
}

w_in = 64

ARGS = {
    'cx': cx,
    'w_in': w_in
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
complexity_conv2d Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/model/complexity.py
code served (permissive licence) · get_code("a2c61cf1be6f496a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function takes a complexity dict and updates it with Conv2D complexity metrics
# cx is a dict with keys: 'h', 'w', 'flops', 'params', 'acts'
# All other parameters are integers or booleans

cx = {
    'h': 32,
    'w': 32,
    'flops': 0,
    'params': 0,
    'acts': 0
}

w_in = 3
w_out = 64
k = 3
s = 1
p = 1
g = 1
b = True

ARGS = {
    'cx': cx,
    'w_in': w_in,
    'w_out': w_out,
    'k': k,
    's': s,
    'p': p,
    'g': g,
    'b': b
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
complexity_maxpool2d Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/model/complexity.py
code served (permissive licence) · get_code("a7c0f04b031c05be")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Build a minimal complexity dict that represents the state of a layer
cx = {
    'h': 32,           # height
    'w': 64,           # width
    'flops': 1000,     # floating point operations
    'params': 500,     # parameters
    'acts': 200        # activations
}

# MaxPool2D parameters
k = 2   # kernel size
s = 2   # stride
p = 0   # padding

ARGS = {
    'cx': cx,
    'k': k,
    's': s,
    'p': p
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv1x1 Ran
ran; our contract draft was wrong, not the code
ZHANGHeng19931123/MutualGuide/models/backbone/resnet_backbone.py
code served (permissive licence) · get_code("d9def42110729a85")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv3x3 Ran
ran; our contract draft was wrong, not the code
ZHANGHeng19931123/MutualGuide/models/backbone/resnet_backbone.py
code served (permissive licence) · get_code("160bb14bd76201b4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "groups": 1,
    "dilation": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv_bn Ran
ran; our contract draft was wrong, not the code
ZHANGHeng19931123/MutualGuide/models/backbone/repvgg_backbone.py
code served (permissive licence) · get_code("7186655759897af6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'in_channels': 3,
    'out_channels': 64,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'groups': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_act_layer Ran
ran on a synthesized input
ZHANGHeng19931123/MutualGuide/models/backbone/gpunet_backbone.py
code served (permissive licence) · get_code("c0ebab789418c9e4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned type. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "i": 0,
    "inplace": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
drop_connect Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ZHANGHeng19931123/MutualGuide/models/backbone/efficientnet_backbone.py
code served (permissive licence) · get_code("45eada2b88e70500")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small 4D tensor (batch_size=2, channels=4, height=3, width=3)
inputs = torch.randn(2, 4, 3, 3, dtype=torch.float32)

# Drop probability
p = 0.5

# Training mode flag
training = True

ARGS = {
    "inputs": inputs,
    "p": p,
    "training": training
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 4, 3, 3) — shape (2, 4, 3, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
generate_regenet_arch Ran
ran on a synthesized input
wilile26811249/RegNet/models/Regnet.py
code served (permissive licence) · get_code("9ae24bb873bceeb8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    'initial_width': 32,
    'width_slope': 0.5,
    'quantilize': 8,
    'width_m': 2.0,
    'depth': 16,
    'bottleneck_ratio': 4,
    'group_width': 16
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_log_filename Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/log_output.py
code served (permissive licence) · get_code("984a028631f19887")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
from datetime import datetime
import tempfile

# Create a temporary directory for logging
log_dir = tempfile.mkdtemp()

# Define arguments for get_log_filename
ARGS = {
    'log_dir': log_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_logger Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/common.py
code served (permissive licence) · get_code("e9cdcc13fe49820c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Logger. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import sys
import logging

# The function get_logger takes a single parameter: name (a string)
# It uses this name to create a logger via logging.getLogger(name)
# No complex objects needed - just a simple string

ARGS = {
    "name": "test_logger"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_lr Ran
ran, honoured the contract we drafted
wilile26811249/RegNet/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from yjzhang96/UTI-VFI, is pointer only (licence: NONE) · get_code("7337f1f5ff01dcd0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from yjzhang96/UTI-VFI, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_mean_and_std Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/dataset.py
code served (permissive licence) · get_code("d2c4ab4309330f86")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch.utils import data as Data

torch.manual_seed(0)

class SimpleDataset(Data.Dataset):
    def __init__(self, num_samples=2):
        self.num_samples = num_samples
    
    def __len__(self):
        return self.num_samples
    
    def __getitem__(self, idx):
        # Return (image, label) tuple
        # Image: 3 channels, 4x4 spatial dimensions
        img = torch.randn(3, 4, 4)
        lbl = torch.tensor(idx % 2)
        return img, lbl

dataset = SimpleDataset(num_samples=2)

ARGS = {
    'dataset': dataset
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_padding Ran
ran, honoured the contract we drafted
ZHANGHeng19931123/MutualGuide/models/backbone/gpunet_backbone.py
pointer only (licence: MIT); the stored copy get_code serves, from facebookresearch/depthshrinker, is pointer only (licence: NOASSERTION) · get_code("73876e077d3acdf5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from facebookresearch/depthshrinker, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_same_padding Ran
ran, honoured the contract we drafted
ZHANGHeng19931123/MutualGuide/models/backbone/gpunet_backbone.py
pointer only (licence: MIT); the stored copy get_code serves, from facebookresearch/depthshrinker, is pointer only (licence: NOASSERTION) · get_code("54e11386110ff042")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from facebookresearch/depthshrinker, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_stages_from_blocks Ran
ran on a synthesized input
yhhhli/regnet-pytorch/CIFAR10/models/regnet.py
code served (permissive licence) · get_code("cf37365adf0e1e42")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Analyze the function to understand what it needs:
# - ws: appears to be a list/sequence that gets concatenated with [0]
# - rs: appears to be a list/sequence that gets concatenated with [0]
# The function compares consecutive elements to detect stage boundaries
# It returns stage widths and stage depths

# Create simple test data
ws = [64, 64, 128, 128, 256]  # widths at each block
rs = [2, 2, 4, 4, 8]           # some values at each block

ARGS = {
    "ws": ws,
    "rs": rs,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_test_log_filename Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/log_output.py
code served (permissive licence) · get_code("71ed90ac72db0a23")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
from datetime import datetime
import tempfile

# Create a temporary directory for the log
log_dir = tempfile.mkdtemp()

ARGS = {
    "log_dir": log_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
horizontal_flip Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/transform.py
code served (permissive licence) · get_code("d401541fae28c8df")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family float, shape (3, 4, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

np.random.seed(0)

# Create a small test image in CHW format
# Channels=3, Height=4, Width=5
img_chw = np.random.rand(3, 4, 5)

# Create a small test image in HWC format
# Height=4, Width=5, Channels=3
img_hwc = np.random.rand(4, 5, 3)

# Probability of flip
p = 0.7

# Test with CHW format
ARGS = {
    'img': img_chw,
    'p': p,
    'order': 'CHW'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (3, 4, 5) — shape (3, 4, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_cfg Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/parse_cfg.py
code served (permissive licence) · get_code("de7df4cd7f7cb239")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import yaml
import os

# Create a temporary YAML config file
temp_dir = tempfile.mkdtemp()
cfg_path = os.path.join(temp_dir, "config.yaml")

# Write a valid YAML configuration
config_data = {
    "model": "test_model",
    "batch_size": 32,
    "learning_rate": 0.001,
    "epochs": 10,
    "layers": [64, 128, 256]
}

with open(cfg_path, 'w') as f:
    yaml.dump(config_data, f)

ARGS = {
    "cfg_path": cfg_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_checkpoint Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/checkpoint.py
code served (permissive licence) · get_code("0fe8c6f466ab4c72")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import torch
import torch.nn as nn
import tempfile

torch.manual_seed(0)

# Create a minimal model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create a model wrapper for multi-GPU case
class ModelWrapper(nn.Module):
    def __init__(self, model):
        super().__init__()
        self.module = model
    
    def forward(self, x):
        return self.module(x)

# Create a simple optimizer
model = SimpleModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create a valid checkpoint file
checkpoint_data = {
    'state_dict': model.state_dict(),
    'optimizer': optimizer.state_dict(),
    'epoch': 5
}

# Write checkpoint to a temporary file
with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.pt') as f:
    checkpoint_file = f.name

torch.save(checkpoint_data, checkpoint_file)

# Create a fresh model and optimizer for loading
fresh_model = SimpleModel()
fresh_optimizer = torch.optim.SGD(fresh_model.parameters(), lr=0.01)

ARGS = {
    'checkpoint_file': checkpoint_file,
    'gpu_num': 1,
    'model': fresh_model,
    'optimizer': fresh_optimizer
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_image Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/dataset.py
code served (permissive licence) · get_code("086239779f8ee4d5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (4, 3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from PIL import Image
import tempfile
import os

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.png")

# Create a small test image (4x3 RGB)
test_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
test_image = Image.fromarray(test_array, mode='RGB')
test_image.save(temp_image_path)

ARGS = {
    'filepath': temp_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (4, 3, 3) — shape (4, 3, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
lr_policy_cos Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/lr_policy.py
code served (permissive licence) · get_code("4cc9b1db1b0d55b6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    "epoch_i": 5,
    "base_lr": 0.1,
    "max_epoch": 100,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
lr_policy_exp Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/lr_policy.py
code served (permissive licence) · get_code("d37a1ce2bc6180e6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    "epoch_i": 5,
    "base_lr": 0.1,
    "gamma": 0.95
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
lr_policy_steps Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/lr_policy.py
code served (permissive licence) · get_code("cb66896e95a24c22")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

ARGS = {
    "epoch_i": 5,
    "base_lr": 0.1,
    "milestone": [0, 2, 4, 6],
    "lr_mult": 0.1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
multibox Ran
ran on a synthesized input
ZHANGHeng19931123/MutualGuide/models/detector.py
code served (permissive licence) · get_code("11d3877a0ccf3ee3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleConvBlock(nn.Module):
    """Minimal conv block that accepts (in_channels, out_channels, kernel_size, padding)"""
    def __init__(self, in_channels, out_channels, kernel_size, padding=0):
        super().__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, padding=padding)
    
    def forward(self, x):
        return self.conv(x)

ARGS = {
    'fpn_level': 3,
    'num_anchors': 6,
    'num_classes': 21,
    'fea_channel': 256,
    'dis_channel': 4,
    'conv_block': SimpleConvBlock
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
quantize_float Ran
ran on a synthesized input
yhhhli/regnet-pytorch/CIFAR10/models/regnet.py
code served (permissive licence) · get_code("a7f56f01db1812a0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    "f": 3.7,
    "q": 0.5,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
round_filters Ran
ran, honoured the contract we drafted
ZHANGHeng19931123/MutualGuide/models/backbone/efficientnet_backbone.py
code served (permissive licence) · get_code("fea14f1f6c2644bf")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

class GlobalParams:
    def __init__(self, width_coefficient, depth_divisor, min_depth):
        self.width_coefficient = width_coefficient
        self.depth_divisor = depth_divisor
        self.min_depth = min_depth

global_params = GlobalParams(
    width_coefficient=1.2,
    depth_divisor=8,
    min_depth=16
)

ARGS = {
    "filters": 32,
    "global_params": global_params
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
round_repeats Ran
ran, honoured the contract we drafted
ZHANGHeng19931123/MutualGuide/models/backbone/efficientnet_backbone.py
pointer only (licence: MIT); the stored copy get_code serves, from Klassikcat/project-NEXTLab-CNN-EfficientNet, is pointer only (licence: NONE) · get_code("f93cb693ac8bb537")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Klassikcat/project-NEXTLab-CNN-EfficientNet, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

save_checkpoint Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/checkpoint.py
code served (permissive licence) · get_code("a0cc9cf5cccaf75a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import torch
import torch.nn as nn
import tempfile

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create a wrapper model to handle both single GPU and multi-GPU cases
class WrappedModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.module = SimpleModel()
    
    def forward(self, x):
        return self.module(x)

# Instantiate the model
model = SimpleModel()

# Create an optimizer
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create temporary directory for checkpoint
checkpoint_dir = tempfile.mkdtemp()

# Define arguments
ARGS = {
    'model': model,
    'optimizer': optimizer,
    'epoch': 5,
    'gpu_num': 1,
    'checkpoint_file': checkpoint_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
search_same Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/common.py
code served (permissive licence) · get_code("4d3ce1e2a3d645cb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
import yaml
import numpy as np
import pandas as pd
from types import SimpleNamespace

# Create a temporary directory structure for the test
tmpdir = tempfile.mkdtemp()
dataset_name = "test_dataset"
stamp = "test_stamp_001"

# Create directory structure
dataset_path = os.path.join(tmpdir, dataset_name)
stamp_path = os.path.join(dataset_path, stamp)
checkpoint_path = os.path.join(stamp_path, "checkpoint", "query")
history_path = os.path.join(stamp_path, "history")

os.makedirs(checkpoint_path, exist_ok=True)
os.makedirs(history_path, exist_ok=True)

# Create model_desc.yml with matching parameters
model_desc = {
    'dataset': dataset_name,
    'epochs': 10,
    'batch_size': 32,
    'learning_rate': 0.001,
    'model_type': 'test_model',
    'checkpoint': None,
    'history': None,
    'snapshot': None,
    'summary': None,
    'src_path': '/src',
    'data_path': '/data',
    'result_path': tmpdir,
    'stamp': stamp,
    'gpus': '0',
    'ignore_search': ''
}

with open(os.path.join(stamp_path, 'model_desc.yml'), 'w') as f:
    yaml.dump(model_desc, f)

# Create epoch.csv with training history
history_data = {
    'epoch': [0, 1, 2],
    'train_loss': [1.0, 0.8, 0.6],
    'val_loss': [1.1, 0.9, 0.7]
}
df = pd.DataFrame(history_data)
df.to_csv(os.path.join(history_path, 'epoch.csv'), index=False)

# Create a checkpoint file
checkpoint_file = os.path.join(checkpoint_path, '3_checkpoint.h5')
with open(checkpoint_file, 'w') as f:
    f.write('dummy checkpoint')

# Build args namespace
args = SimpleNamespace(
    dataset=dataset_name,
    result_path=tmpdir,
    epochs=10,
    batch_size=32,
    learning_rate=0.001,
    model_type='test_model',
    checkpoint=None,
    history=None,
    snapshot=None,
    summary=None,
    src_path='/src',
    data_path='/data',
    stamp=None,
    gpus='0',
    ignore_search=''
)

ARGS = {
    'args': args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas, yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
select_config Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/search_space.py
code served (permissive licence) · get_code("113ee8ba2c42d3b4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import copy
import random

# Set seed for reproducibility
random.seed(42)

# Create a valid config dictionary that satisfies all assertions
cfg = {
    'n_stage': 3,  # Number of stages
    'n_block': [2, 5],  # min=2 (>0), max=5; will select 3 random values (one per stage)
    'n_channel': [16, 64],  # min=16 (divisible by 8), max=64; will select 3 random values (one per stage)
    'bottleneck_ratio': [2, 4, 8],  # List to choose from
    'group_width': [1, 2, 4],  # List to choose from
}

ARGS = {
    'cfg': cfg
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
set_dataset Ran
ran on a synthesized input
PaperCodeReview/RegNet-TF/dataloader.py
code served (permissive licence) · get_code("efceaef7f38bd7b9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import numpy as np
import pandas as pd
import pickle
import tempfile

# Create a temporary directory and mock CIFAR data files
tmpdir = tempfile.mkdtemp()

# Create mock CIFAR train batch file
train_data = {
    b'data': np.random.randint(0, 256, size=(4, 3072), dtype=np.uint8),
    b'fine_labels': [0, 1, 0, 2]
}
with open(os.path.join(tmpdir, 'train'), 'wb') as f:
    pickle.dump(train_data, f)

# Create mock CIFAR test batch file
test_data = {
    b'data': np.random.randint(0, 256, size=(2, 3072), dtype=np.uint8),
    b'fine_labels': [1, 2]
}
with open(os.path.join(tmpdir, 'test'), 'wb') as f:
    pickle.dump(test_data, f)

# Create mock args object
class Args:
    def __init__(self, dataset, data_path):
        self.dataset = dataset
        self.data_path = data_path

ARGS = {
    'args': Args(dataset='cifar100', data_path=tmpdir)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
trunc_normal_ Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ZHANGHeng19931123/MutualGuide/models/backbone/swin_backbone.py
code served (permissive licence) · get_code("af8aefa30bd76920")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import math
import warnings

torch.manual_seed(0)

# Create a small tensor to initialize
tensor = torch.randn(2, 4)

# Define all parameters for trunc_normal_
ARGS = {
    'tensor': tensor,
    'mean': 0.0,
    'std': 1.0,
    'a': -2.0,
    'b': 2.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ZHANGHeng19931123/MutualGuide/models/backbone/swin_backbone.py
pointer only (licence: MIT); the stored copy get_code serves, from xuwayyy/SHARE, is pointer only (licence: NONE) · get_code("f6b2d702fc756d64")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xuwayyy/SHARE, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

window_reverse Ran
ran; our contract draft was wrong, not the code
ZHANGHeng19931123/MutualGuide/models/backbone/swin_backbone.py
pointer only (licence: MIT); the stored copy get_code serves, from xuwayyy/SHARE, is pointer only (licence: NONE) · get_code("7b0d02f75bf6b439")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xuwayyy/SHARE, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

zero_pad Ran
ran on a synthesized input
Alessiacosmos/Basic-RegNet-pytorch/utils/transform.py
code served (permissive licence) · get_code("94d1acf6801b9a00")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family float, shape (3, 8, 9) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small test image with shape (channels, height, width)
# Using distinct dimensions: 3 channels, 4 height, 5 width
img = np.random.rand(3, 4, 5).astype(np.float32)

# Pad size
pad_size = 2

ARGS = {
    'img': img,
    'pad_size': pad_size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (3, 8, 9) — shape (3, 8, 9) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
accuracy Not yet run
unverified (harvested, no recorded run)
Alessiacosmos/Basic-RegNet-pytorch/utils/evalutator.py
code served (permissive licence) · get_code("26219ca9c20a331d")
How it ran

no invocation recorded.

callback_tensorboard Not yet run
unverified (harvested, no recorded run)
PaperCodeReview/RegNet-TF/callback.py
code served (permissive licence) · get_code("a937bb237ee86019")
How it ran

no invocation recorded.

get_cifar10_dataset Not yet run
unverified (harvested, no recorded run)
wilile26811249/RegNet/utils.py
code served (permissive licence) · get_code("ba1d6e8ebcd04bd9")
How it ran

no invocation recorded.

topk_correct Not yet run
unverified (harvested, no recorded run)
Alessiacosmos/Basic-RegNet-pytorch/utils/evalutator.py
code served (permissive licence) · get_code("524aef024eb6924a")
How it ran

no invocation recorded.

topk_error Not yet run
unverified (harvested, no recorded run)
Alessiacosmos/Basic-RegNet-pytorch/utils/evalutator.py
code served (permissive licence) · get_code("58f32cb0086a5fbf")
How it ran

no invocation recorded.

Also present in other papers' code

Of 53 samples lifted from this paper's linked repositories, 53 carry a function identity and 0 do not. Of the 53 distinct functions with an identity, 19 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 4 the same month, 18 later) and 34 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conv1x1 431 other papers
59 dated earlier, 12 the same month, 359 later, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
30 dated earlier, 8 the same month, 273 later, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
window_reverse 227 other papers
2 dated earlier, 225 later · 34 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
1711.10925 (2017-11)
Deep Image Prior
2007.09384 (2020-07)
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
and 224 more not named here
window_partition 223 other papers
2 dated earlier, 221 later · 32 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1711.10925 (2017-11)
Deep Image Prior
2007.09384 (2020-07)
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
and 220 more not named here
round_filters 31 other papers
5 dated earlier, 26 later · 3 only as an assembly brick
1808.08127 (2018-08)
Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
1911.09070 (2019-11)
EfficientDet: Scalable and Efficient Object Detection
and 28 more not named here
round_repeats 30 other papers
5 dated earlier, 25 later · 3 only as an assembly brick
1808.08127 (2018-08)
Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
1911.09070 (2019-11)
EfficientDet: Scalable and Efficient Object Detection
and 27 more not named here
get_lr 25 other papers
4 dated earlier, 21 later · 2 only as an assembly brick
1605.07148 (2016-05)
Backprop KF: Learning Discriminative Deterministic State Estimators
1606.00915 (2016-06)
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
and 22 more not named here
channel_shuffle 19 other papers
8 dated earlier, 11 later · 2 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1606.02147 (2016-06)
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
1805.12549 (2018-05)
Channel Gating Neural Networks
and 16 more not named here
drop_connect 15 other papers
3 dated earlier, 12 later · 2 only as an assembly brick
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
1911.09070 (2019-11)
EfficientDet: Scalable and Efficient Object Detection
1912.06218 (2019-12)
YOLACT++: Better Real-time Instance Segmentation
and 12 more not named here
conv_bn 10 other papers
10 later
2101.03697 (2021-01)
RepVGG: Making VGG-style ConvNets Great Again
2105.01883 (2021-05)
RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition
2112.11081 (2021-12)
RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality
and 7 more not named here
get_same_padding 4 other papers
4 later
2203.10233 (2022-03)
DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
2206.00843 (2022-06)
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
2407.03179 (2024-07)
Motion meets Attention: Video Motion Prompts
and 1 more not named here
complexity_batchnorm2d 3 other papers
1 dated earlier, 2 later
1905.13214 (2019-05)
On Network Design Spaces for Visual Recognition
2108.02927 (2021-08)
DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features
2308.04008 (2023-08)
Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrieval
get_padding 3 other papers
3 later · 1 only as an assembly brick
2104.08215 (2021-04)
"BNN - BN = ?": Training Binary Neural Networks without Batch Normalization
2204.02844 (2022-04)
Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training
2206.00843 (2022-06)
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
get_logger 2 other papers
1 the same month, 1 later
2003.04297 (2020-03)
Improved Baselines with Momentum Contrastive Learning
2004.11362 (2020-04)
Supervised Contrastive Learning
adjust_ws_gs_comp 1 other paper
1 later
2303.11906 (2023-03)
Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
check_arguments 1 other paper
1 the same month
2003.04297 (2020-03)
Improved Baselines with Momentum Contrastive Learning
get_stages_from_blocks 1 other paper
1 later
2303.11906 (2023-03)
Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
quantize_float 1 other paper
1 later
2303.11906 (2023-03)
Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
trunc_normal_ 1 other paper
1 later
2405.14791 (2024-05)
Recurrent Early Exits for Federated Learning with Heterogeneous Clients

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this work, we present a new network design paradigm. Our goal is to help advance the understanding of network design and discover design principles that generalize across settings. Instead of focusing on designing individual network instances, we design network design spaces that parametrize populations of networks. The overall process is analogous to classic manual design of networks, but elevated to the design space level. Using our methodology we explore the structure aspect of network design and arrive at a low-dimensional design space consisting of simple, regular networks that we call RegNet. The core insight of the RegNet parametrization is surprisingly simple: widths and depths of good networks can be explained by a quantized linear function. We analyze the RegNet design space and arrive at interesting findings that do not match the current practice of network design. The RegNet design space provides simple and fast networks that work well across a wide range of flop regimes. Under comparable training settings and flops, the RegNet models outperform the popular EfficientNet models while being up to 5x faster on GPUs.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2003.13678")
get_code_for_paper("2003.13678")
have("2003.13678")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2003.13678.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2003.13678.svg)](https://syntology.ai/paper/2003.13678)

Connect an agent — have() is free.